
#Importation of all the needed libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb
import nbconvert
%matplotlib inline


#loading the data sets
loans = pd.read_csv('ProsperLoanData.csv')


#Assessment of the data
loans.head()
loans.info()
loans.describe
loans.shape

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 113937 entries, 0 to 113936
Data columns (total 81 columns):
 #   Column                               Non-Null Count   Dtype  
---  ------                               --------------   -----  
 0   ListingKey                           113937 non-null  object 
 1   ListingNumber                        113937 non-null  int64  
 2   ListingCreationDate                  113937 non-null  object 
 3   CreditGrade                          28953 non-null   object 
 4   Term                                 113937 non-null  int64  
 5   LoanStatus                           113937 non-null  object 
 6   ClosedDate                           55089 non-null   object 
 7   BorrowerAPR                          113912 non-null  float64
 8   BorrowerRate                         113937 non-null  float64
 9   LenderYield                          113937 non-null  float64
 10  EstimatedEffectiveYield              84853 non-null   float64
 11  EstimatedLoss                        84853 non-null   float64
 12  EstimatedReturn                      84853 non-null   float64
 13  ProsperRating (numeric)              84853 non-null   float64
 14  ProsperRating (Alpha)                84853 non-null   object 
 15  ProsperScore                         84853 non-null   float64
 16  ListingCategory (numeric)            113937 non-null  int64  
 17  BorrowerState                        108422 non-null  object 
 18  Occupation                           110349 non-null  object 
 19  EmploymentStatus                     111682 non-null  object 
 20  EmploymentStatusDuration             106312 non-null  float64
 21  IsBorrowerHomeowner                  113937 non-null  bool   
 22  CurrentlyInGroup                     113937 non-null  bool   
 23  GroupKey                             13341 non-null   object 
 24  DateCreditPulled                     113937 non-null  object 
 25  CreditScoreRangeLower                113346 non-null  float64
 26  CreditScoreRangeUpper                113346 non-null  float64
 27  FirstRecordedCreditLine              113240 non-null  object 
 28  CurrentCreditLines                   106333 non-null  float64
 29  OpenCreditLines                      106333 non-null  float64
 30  TotalCreditLinespast7years           113240 non-null  float64
 31  OpenRevolvingAccounts                113937 non-null  int64  
 32  OpenRevolvingMonthlyPayment          113937 non-null  float64
 33  InquiriesLast6Months                 113240 non-null  float64
 34  TotalInquiries                       112778 non-null  float64
 35  CurrentDelinquencies                 113240 non-null  float64
 36  AmountDelinquent                     106315 non-null  float64
 37  DelinquenciesLast7Years              112947 non-null  float64
 38  PublicRecordsLast10Years             113240 non-null  float64
 39  PublicRecordsLast12Months            106333 non-null  float64
 40  RevolvingCreditBalance               106333 non-null  float64
 41  BankcardUtilization                  106333 non-null  float64
 42  AvailableBankcardCredit              106393 non-null  float64
 43  TotalTrades                          106393 non-null  float64
 44  TradesNeverDelinquent (percentage)   106393 non-null  float64
 45  TradesOpenedLast6Months              106393 non-null  float64
 46  DebtToIncomeRatio                    105383 non-null  float64
 47  IncomeRange                          113937 non-null  object 
 48  IncomeVerifiable                     113937 non-null  bool   
 49  StatedMonthlyIncome                  113937 non-null  float64
 50  LoanKey                              113937 non-null  object 
 51  TotalProsperLoans                    22085 non-null   float64
 52  TotalProsperPaymentsBilled           22085 non-null   float64
 53  OnTimeProsperPayments                22085 non-null   float64
 54  ProsperPaymentsLessThanOneMonthLate  22085 non-null   float64
 55  ProsperPaymentsOneMonthPlusLate      22085 non-null   float64
 56  ProsperPrincipalBorrowed             22085 non-null   float64
 57  ProsperPrincipalOutstanding          22085 non-null   float64
 58  ScorexChangeAtTimeOfListing          18928 non-null   float64
 59  LoanCurrentDaysDelinquent            113937 non-null  int64  
 60  LoanFirstDefaultedCycleNumber        16952 non-null   float64
 61  LoanMonthsSinceOrigination           113937 non-null  int64  
 62  LoanNumber                           113937 non-null  int64  
 63  LoanOriginalAmount                   113937 non-null  int64  
 64  LoanOriginationDate                  113937 non-null  object 
 65  LoanOriginationQuarter               113937 non-null  object 
 66  MemberKey                            113937 non-null  object 
 67  MonthlyLoanPayment                   113937 non-null  float64
 68  LP_CustomerPayments                  113937 non-null  float64
 69  LP_CustomerPrincipalPayments         113937 non-null  float64
 70  LP_InterestandFees                   113937 non-null  float64
 71  LP_ServiceFees                       113937 non-null  float64
 72  LP_CollectionFees                    113937 non-null  float64
 73  LP_GrossPrincipalLoss                113937 non-null  float64
 74  LP_NetPrincipalLoss                  113937 non-null  float64
 75  LP_NonPrincipalRecoverypayments      113937 non-null  float64
 76  PercentFunded                        113937 non-null  float64
 77  Recommendations                      113937 non-null  int64  
 78  InvestmentFromFriendsCount           113937 non-null  int64  
 79  InvestmentFromFriendsAmount          113937 non-null  float64
 80  Investors                            113937 non-null  int64  
dtypes: bool(3), float64(50), int64(11), object(17)
memory usage: 68.1+ MB

(113937, 81)


pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows',None)


loans.head()
loans.IncomeVerifiable.value_counts()

True     105268
False      8669
Name: IncomeVerifiable, dtype: int64


loans.LoanStatus.isnull().sum()

0


loans.CreditGrade.isnull().sum()

84984


#To display the columns
loans.columns

Index(['ListingKey', 'ListingNumber', 'ListingCreationDate', 'CreditGrade',
       'Term', 'LoanStatus', 'ClosedDate', 'BorrowerAPR', 'BorrowerRate',
       'LenderYield', 'EstimatedEffectiveYield', 'EstimatedLoss',
       'EstimatedReturn', 'ProsperRating (numeric)', 'ProsperRating (Alpha)',
       'ProsperScore', 'ListingCategory (numeric)', 'BorrowerState',
       'Occupation', 'EmploymentStatus', 'EmploymentStatusDuration',
       'IsBorrowerHomeowner', 'CurrentlyInGroup', 'GroupKey',
       'DateCreditPulled', 'CreditScoreRangeLower', 'CreditScoreRangeUpper',
       'FirstRecordedCreditLine', 'CurrentCreditLines', 'OpenCreditLines',
       'TotalCreditLinespast7years', 'OpenRevolvingAccounts',
       'OpenRevolvingMonthlyPayment', 'InquiriesLast6Months', 'TotalInquiries',
       'CurrentDelinquencies', 'AmountDelinquent', 'DelinquenciesLast7Years',
       'PublicRecordsLast10Years', 'PublicRecordsLast12Months',
       'RevolvingCreditBalance', 'BankcardUtilization',
       'AvailableBankcardCredit', 'TotalTrades',
       'TradesNeverDelinquent (percentage)', 'TradesOpenedLast6Months',
       'DebtToIncomeRatio', 'IncomeRange', 'IncomeVerifiable',
       'StatedMonthlyIncome', 'LoanKey', 'TotalProsperLoans',
       'TotalProsperPaymentsBilled', 'OnTimeProsperPayments',
       'ProsperPaymentsLessThanOneMonthLate',
       'ProsperPaymentsOneMonthPlusLate', 'ProsperPrincipalBorrowed',
       'ProsperPrincipalOutstanding', 'ScorexChangeAtTimeOfListing',
       'LoanCurrentDaysDelinquent', 'LoanFirstDefaultedCycleNumber',
       'LoanMonthsSinceOrigination', 'LoanNumber', 'LoanOriginalAmount',
       'LoanOriginationDate', 'LoanOriginationQuarter', 'MemberKey',
       'MonthlyLoanPayment', 'LP_CustomerPayments',
       'LP_CustomerPrincipalPayments', 'LP_InterestandFees', 'LP_ServiceFees',
       'LP_CollectionFees', 'LP_GrossPrincipalLoss', 'LP_NetPrincipalLoss',
       'LP_NonPrincipalRecoverypayments', 'PercentFunded', 'Recommendations',
       'InvestmentFromFriendsCount', 'InvestmentFromFriendsAmount',
       'Investors'],
      dtype='object')


# subsetting relevant columns
useful_cols =['EstimatedReturn','LoanStatus','StatedMonthlyIncome','IncomeRange','DelinquenciesLast7Years','Term','AmountDelinquent',
              'ProsperScore','CreditGrade',
             'EmploymentStatus','EmploymentStatusDuration','IsBorrowerHomeowner','CreditScoreRangeLower',
              'CreditScoreRangeUpper',
             'CurrentCreditLines','OpenCreditLines','RevolvingCreditBalance',
              'DebtToIncomeRatio','BorrowerAPR','BorrowerRate',
              'AvailableBankcardCredit','ProsperRating (Alpha)','ProsperRating (numeric)','LoanOriginalAmount']
factors= loans[useful_cols]


#sum of rows with null borrower APR 
factors.BorrowerAPR.isnull().sum()

25


#displaying the rows with null values for borrower APR
null_APR = pd.isnull(factors["BorrowerAPR"])
factors[null_APR]


#dropping rows with null values for Borrower APR
factors = factors[~factors.BorrowerAPR.isna()]


#testing
factors.BorrowerAPR.isnull().sum()

0


factors.head()


#summary statistics of the numerical variables
factors.describe()


#use of histogram plots to show the distribution of borrowerAPR
plt.figure(figsize =[10,8])
bins= np.arange(0,factors.BorrowerAPR.max()+ 0.005,0.01)
plt.title("BorrowerAPR distribution across counts")
plt.hist(factors['BorrowerAPR'],bins = bins);


fig, ax = plt.subplots(nrows=2, figsize = [10,10])
default_color = sb.color_palette()[0]
sb.histplot(data = factors,x = 'BorrowerAPR',ax = ax[0]).set_title('BorrowerAPR distribution across counts')
plt.ylim(0,7500)
sb.histplot(data = factors,x = 'BorrowerRate',ax = ax[1]).set_title('Borrower Rate distribution across counts')

Text(0.5, 1.0, 'Borrower Rate distribution across counts')


#seaborn is used again to give a more detailed distribution and summary of IncomeRange
sb.histplot(data = factors,y = 'IncomeRange').set_title('Income Range Count')
plt.xticks(
    rotation=45, 
    horizontalalignment='right',
    fontweight='light',
    fontsize='small');


#setting the dimensions
fig, ax = plt.subplots(figsize=(10, 6))
#drawing the plot
sb.histplot(data = factors , x ='LoanOriginalAmount',binwidth =500).set_title('Count of Original loan Amount')
plt.xlim(0,36000)
plt.show()


#credit score creation using creditscore range upper and creditscore range lower.
#factors['creditscore'] = (factors["CreditScoreRangeUpper"]+factors["CreditScoreLower"]).mean(axis =1)
factors["creditscore"] = factors[["CreditScoreRangeUpper", "CreditScoreRangeLower"]].mean(axis=1)


factors.creditscore.value_counts()
plt.figure(figsize=(15,7))
sb.countplot(data= factors, x= "creditscore").set_title("Distribution of credit Score")
plt.xticks(rotation = 90);


#creating a subset and dropping such rows of data.
credit_score_high = factors[(factors['creditscore']==9.5)].index
credit_score_high

Int64Index([   794,    912,   1685,   4290,   4371,   4430,   4672,   5684,
              6877,   7739,
            ...
            105032, 106897, 108762, 109060, 109468, 109522, 109855, 110290,
            111624, 113848],
           dtype='int64', length=133)


#dropping the rows
factors.drop(credit_score_high,inplace = True)


#checking the distribution after removing the outlier
factors.creditscore.value_counts()
plt.figure(figsize=(15,7))
sb.countplot(data= factors, x= "creditscore").set_title("Distribution of credit Score")
plt.xticks(rotation = 90);


#distribution of stated Monthly income
plt.figure(figsize=(10,7))
bins_smi = np.arange(0, 50000, 500)
plt.hist(data = factors, x = 'StatedMonthlyIncome', bins=bins_smi);
plt.title('Distribution of borrowers Stated Monthly Income')
plt.xlim(0,45000)

(0.0, 45000.0)


factors.Term.value_counts()

36    87620
60    24545
12     1614
Name: Term, dtype: int64


# Convert ProsperRating and Employment status into ordered categorical types
rate_order = ['HR','E','D','C','B','A','AA']
ordered_var = pd.api.types.CategoricalDtype(ordered = True,
                                    categories = rate_order)
factors['ProsperRating (Alpha)'] = factors['ProsperRating (Alpha)'].astype(ordered_var)

emp_order = ['Employed','Self-employed','Full-time','Part-time','Retired','Other','Not employed', 'Not available']
ordered_var = pd.api.types.CategoricalDtype(ordered = True,
                                    categories = emp_order)
factors['EmploymentStatus'] = factors['EmploymentStatus'].astype(ordered_var)


fig, ax = plt.subplots(nrows=3, figsize = [8,8])
default_color = sb.color_palette()[0]
type_order = factors['Term'].value_counts().index
sb.countplot(data = factors, x = 'Term', color = default_color, order=type_order, ax = ax[0]).set_title('Count of Loan Duration')
sb.countplot(data = factors, x = 'ProsperRating (Alpha)', color = default_color, ax = ax[1]).set_title('Count of Prosper rating ')
sb.countplot(data = factors, x = 'EmploymentStatus', color = default_color, ax = ax[2]).set_title('count of Employment Status');
plt.xticks(rotation=30);
plt.subplots_adjust(left=0.1,
                    bottom=0.1,
                    right=0.9,
                    top=0.9,
                    wspace=0.4,
                    hspace=0.4)


default_color = sb.color_palette()[3]
sb.countplot(data = factors, x = 'ProsperScore', color = default_color).set_title('Count of Prosper Score ')

Text(0.5, 1.0, 'Count of Prosper Score ')


factors.query('ProsperScore > 10')


#creating a subset and dropping such rows of data.
prosper_score_high = factors[(factors['ProsperScore']> 10)].index
prosper_score_high
#dropping such rows
factors.drop(prosper_score_high,inplace = True)


#testing drop
factors.query('ProsperScore > 10')


#checking the plot after the drop
default_color = sb.color_palette()[3]
sb.countplot(data = factors, x = 'ProsperScore', color = default_color).set_title('Count of Prosper Score ')

Text(0.5, 1.0, 'Count of Prosper Score ')


x=np.array([10000,20000,30000,40000,50000,60000,70000,80000,90000])
fig, ax = plt.subplots(nrows=1, figsize = [8,8])
default_color = sb.color_palette()[0]
sb.histplot(data =factors,x ='AmountDelinquent',color= default_color).set_title('Distribution of borrowers deliquent Amount')
plt.xlim(0,110000);


x=np.array([5,10,15,20,25,30,35,40,45,60,65,70,75])
plt.figure(figsize =(12,6))
plt.title('Distribution of borrowers Delinquencies in past 7years');
plt.hist(data= factors, x= 'DelinquenciesLast7Years')
plt.xlim(0,70)
plt.xticks(x);


plt.subplots(figsize=[8,8])
plt.title('Distribution of Borrowers Current credit lines')
plt.hist(data = factors, x = 'CurrentCreditLines')
plt.xlabel('CurrentCreditLines')
plt.xlim(0,45);


plt.figure(figsize =(8,8))
x= np.array([5,10,15,20,25,30,35,40])
plt.hist(data = factors, x = 'OpenCreditLines');
plt.xticks(x)
plt.xlabel('Open credit lines')
plt.xlim(0,40)
plt.title('Distribution of open credit lines')

Text(0.5, 1.0, 'Distribution of open credit lines')


plt.figure(figsize=(10,5))
sb.histplot(data = factors, x = 'RevolvingCreditBalance',binwidth =3500)
plt.title('Distribution of Revolving credit balance')
plt.xlim(0,270000)

(0.0, 270000.0)


plt.title("Distribution of Avaialable bank credit")
plt.hist(data = factors,x ='AvailableBankcardCredit')
plt.xlim(0,150000)
plt.xlabel('Available bank credit')
plt.ylabel('count of available bank credit')

Text(0, 0.5, 'count of available bank credit')


#categorising the data types into numeric and categorical data
num_vars = factors.select_dtypes(include='number').columns
cat_vars = ['Term', 'EmploymentStatus', 'ProsperRating (Alpha)','IsBorrowerHomeowner']


#Correlation between variables
## A heatmap is used to depict a genral overview of the correlartion between all the variables in the data set.
plt.figure(figsize = [10,6])
plt.title('Correlation of all variables')
sb.heatmap(factors[num_vars].corr(), annot = True, fmt = '.2f',
           cmap = 'RdBu',vmin=-1,vmax=1, center = 0)
plt.show()


#A plot to show how closely related the prosperscore and the prosper rating are.
sb.scatterplot(data=factors,x= 'ProsperScore',y='ProsperRating (Alpha)').set_title('Correlation of prosper score and prosper rating')

Text(0.5, 1.0, 'Correlation of prosper score and prosper rating')


plt.figure(figsize = [10, 8])
sb.regplot(data=factors,x= 'creditscore',y='ProsperScore');
plt.title("Correlation of prosper score and amounts requested for loans ");


plt.figure(figsize = [10, 8])
sb.countplot(data=factors, x='ProsperRating (Alpha)', hue='IsBorrowerHomeowner', palette='Dark2');
plt.legend(loc=1);
plt.title("Count of home owning borrowers against Prosper rating ");


plt.figure(figsize = [10, 8])
sb.regplot(data=factors,y= 'LoanOriginalAmount',x='ProsperScore');
plt.title("Correlation of prosper score and amounts requested for loans ");


plt.figure(figsize = [10,8])
sb.countplot(data=factors, x='ProsperRating (Alpha)', hue='EmploymentStatus', palette='Set2');
plt.legend(loc=1);
plt.title("Common Employment Status in each Prosper Rating");


plt.figure(figsize = [10, 8])
sb.regplot(data=factors, y='ProsperScore', x='DebtToIncomeRatio');
plt.ylim(0,15)
plt.xlim(0,10)
plt.title("Correlation of prosperscore and DebtToincome Ratio");


plt.figure(figsize = [10, 8])
sb.regplot(data=factors, y='ProsperScore', x='RevolvingCreditBalance');
plt.title(" Correlation of Prosperscore and Revolving credit balance ");


plt.subplots()
sb.regplot(data=factors,x='StatedMonthlyIncome',y='ProsperScore')
plt.xlim(0,65000)

(0.0, 65000.0)


#There is an outlier that's skewing the plot and i think it needs to be dropped


#fishing out the outlier
factors.StatedMonthlyIncome.max()

1750002.916667


#Dropping the outlier
out_income = factors[(factors['StatedMonthlyIncome']== 1750002.916667)].index
#dropping such rows
factors.drop(out_income,inplace = True)


factors.query('StatedMonthlyIncome ==1750002.916667')


#plotting after the drop
plt.subplots()
sb.regplot(data=factors,x='StatedMonthlyIncome',y='ProsperScore')
plt.xlim(0,65000)
plt.ylim(0,11)

(0.0, 11.0)


sb.lineplot(data = factors, x ='ProsperScore',y='StatedMonthlyIncome').set_title('Correlation of Prosperscore and  StatedMonthly Income')

Text(0.5, 1.0, 'Correlation of Prosperscore and  StatedMonthly Income')


plt.figure(figsize=(8,5))
sb.barplot(data=factors,x='Term',y='ProsperScore', palette='rainbow')
plt.title("Count of prosper score for the loan Terms")

Text(0.5, 1.0, 'Count of prosper score for the loan Terms')


plt.figure(figsize = [10, 8])
sb.regplot(data=factors, y='BorrowerAPR', x='ProsperScore');
plt.title("Correlation of Borrower APR and ProsperScore");
plt.ylim(0.04,0.42)
plt.xlim(0,11)

(0.0, 11.0)


plt.figure(figsize=(12,10))
plt.subplot(2,2,1)
sb.boxenplot(data= factors,x='ProsperRating (Alpha)',y='BorrowerAPR').set_title('Correlation of prosper rating and Annual interest rates')
plt.subplot(2,2,2)
sb.boxenplot(data= factors,x='ProsperRating (Alpha)',y='BorrowerRate').set_title('Correlation of prosper rating and Annual interest rates')

Text(0.5, 1.0, 'Correlation of prosper rating and Annual interest rates')


plt.figure(figsize = [10, 8])
sb.regplot(data=factors, y='BorrowerAPR', x='DebtToIncomeRatio');
plt.ylim(0,0.6)
plt.xlim(0,12)
plt.title("Correlation of Borrower APR and DebtToincome Ratio");


plt.figure(figsize=(8,6))
sb.regplot(data= factors, x='creditscore',y='BorrowerAPR')
plt.title("Correlation of creditscore and Borrower APR")
plt.xlabel('creditscore')
plt.ylabel('BorrowerAPR')
plt.xlim(350,950)# This was used to trim out an outlier that was an obvious error, because creditscores don't get that high.

(350.0, 950.0)


plt.figure(figsize=(8,6))
sb.regplot(data= factors, y='BorrowerAPR',x='DelinquenciesLast7Years')
plt.title("Correlation of Borrower APR and DelinquenciesLast7Years")
plt.xlabel('DelinquenciesLast7Years')
plt.ylabel('BorrowerAPR')

Text(0, 0.5, 'BorrowerAPR')


### Borrower APR and Available bank credit


plt.figure(figsize=(8,6))
sb.regplot(data= factors, y='BorrowerAPR',x='AvailableBankcardCredit',x_jitter=1,y_jitter=1.5)
plt.title("Correlation of Borrower APR and AvailableBankcardCredit")
plt.xlabel('AvailableBankcardCredit')
plt.ylabel('BorrowerAPR')

Text(0, 0.5, 'BorrowerAPR')


plt.figure(figsize=(8,6))
sb.regplot(data= factors, y='BorrowerAPR',x='LoanOriginalAmount',)
plt.title("Correlation of Borrower APR and Loan Original Amount")
plt.xlabel('LoanOriginalAmount')
plt.ylabel('BorrowerAPR')

Text(0, 0.5, 'BorrowerAPR')


plt.figure(figsize=(8,6))
default_color =sb.color_palette()[0]
sb.boxplot(data = factors,x='EmploymentStatus',y='BorrowerAPR',color=default_color).set_title('Borrower APR and Employment Status')
plt.xticks(rotation=45);


plt.figure(figsize=(10,10))
plt.subplot(2,2,1)
sb.boxplot(data= factors, x='Term',y='BorrowerAPR')
plt.title('Correaltion of borrower APR and loan term')
plt.subplot(2,2,2)
sb.boxplot(data= factors, x='Term',y='BorrowerRate')
plt.title('correlation of Borrower rate and loan term')

Text(0.5, 1.0, 'correlation of Borrower rate and loan term')


sb.barplot(data=factors, x='Term',y= 'BorrowerAPR').set_title('Loan Term Apr scores')

Text(0.5, 1.0, 'Loan Term Apr scores')


#Creating a custom function for box plot
def boxgrid(x, y, **Kwargs):
    default_color = sb.color_palette()[2]
    sb.boxplot(x, y, color = default_color)


# creating a custom function for boxen plot
def boxen(x,y, **Kwargs):
    default_color = sb.color_palette()[3]
    sb.boxenplot(x,y, color =default_color)


#Blocking the warnings temporarily
import warnings
warnings.filterwarnings('ignore')


#creation of pairgrid using boxplots
g = sb.PairGrid(factors,y_vars = ['BorrowerRate','BorrowerAPR','LoanOriginalAmount','AvailableBankcardCredit','DebtToIncomeRatio',
                                 'creditscore'], 
                                x_vars = ['Term', 'ProsperRating (Alpha)', 'EmploymentStatus'], height = 3.5, aspect = 1.0)
g.map(boxgrid);
plt.xticks(rotation=45);
g.fig.suptitle('Term,EmploymentStatus & ProsperRating Vs Numerical features');
plt.show();


g=sb.PairGrid(factors,y_vars=['BorrowerRate','BorrowerAPR','LoanOriginalAmount','AvailableBankcardCredit','DebtToIncomeRatio',
                                 'creditscore'], 
                                x_vars = ['Term', 'ProsperRating (Alpha)', 'EmploymentStatus'], height = 3.5, aspect = 1.0)
g.map(boxen);
plt.xticks(rotation=90);
g.fig.suptitle('Term,EmploymentStatus & ProsperRating Vs Numerical features');
plt.show();


### Effect of employment status on loan term and borrower APR.


plt.figure(figsize=(27,12))
plt.subplot(2,2,1)
fg=sb.violinplot(x='Term',y="BorrowerAPR",data=factors, hue='EmploymentStatus', palette='rainbow').set_title('Effect of employment Status on Borrower APR and Loan Term')
plt.show()


sb.pointplot(data=factors, x='ProsperRating (Alpha)', y='BorrowerRate', hue='Term',
                   palette='tab10');
plt.legend(loc=1, title='Employment Status');
plt.title('Effect of loan term on prosper rating and borrower APR');
plt.ylabel(' Borrower Rate');


# Create a pointplot to show how the BorrowerRate changes for different loan Terms
# when split up by ProsperRating
plt.figure(figsize=[8,6])

sb.pointplot(data=factors, x='ProsperRating (Alpha)', y='BorrowerRate', hue='EmploymentStatus',
                   palette='tab10');
plt.legend(loc=1, title='Employment Status');
plt.title('Effect of employment status on prosper rating and borrower APR');
plt.ylabel(' Borrower Rate');


!jupyter nbconvert Explanatory_Loans_Viz.ipynb --to slides --post serve --no-input --no-prompt

	EstimatedReturn	LoanStatus	StatedMonthlyIncome	IncomeRange	DelinquenciesLast7Years	Term	AmountDelinquent	ProsperScore	CreditGrade	EmploymentStatus	EmploymentStatusDuration	IsBorrowerHomeowner	CreditScoreRangeLower	CreditScoreRangeUpper	CurrentCreditLines	OpenCreditLines	RevolvingCreditBalance	DebtToIncomeRatio	BorrowerAPR	BorrowerRate	AvailableBankcardCredit	ProsperRating (Alpha)	ProsperRating (numeric)	LoanOriginalAmount
2543	NaN	Completed	8333.333333	Not displayed	NaN	36	NaN	NaN	HR	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.02685	NaN	0.10000	NaN	NaN	NaN	4200
14632	NaN	Completed	4166.666667	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.09031	NaN	0.06500	NaN	NaN	NaN	2620
25166	NaN	Completed	9166.666667	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.04120	NaN	0.04350	NaN	NaN	NaN	1000
25330	NaN	Completed	7083.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.07707	NaN	0.06395	NaN	NaN	NaN	1500
29773	NaN	Completed	8333.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01923	NaN	0.06000	NaN	NaN	NaN	3000
39870	NaN	Completed	3333.333333	Not displayed	NaN	36	NaN	NaN	C	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.29069	NaN	0.12000	NaN	NaN	NaN	15000
43587	NaN	Completed	18333.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01510	NaN	0.08500	NaN	NaN	NaN	5000
62297	NaN	Completed	10000.000000	Not displayed	NaN	36	NaN	NaN	E	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01783	NaN	0.17000	NaN	NaN	NaN	1000
71280	NaN	Completed	7083.333333	Not displayed	NaN	36	NaN	NaN	C	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.37002	NaN	0.09000	NaN	NaN	NaN	10000
71875	NaN	Completed	4166.666667	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.02343	NaN	0.07000	NaN	NaN	NaN	3000
73945	NaN	Completed	29166.666667	Not displayed	NaN	36	NaN	NaN	HR	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01234	NaN	0.25000	NaN	NaN	NaN	2500
74114	NaN	Completed	9458.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01115	NaN	0.06000	NaN	NaN	NaN	1000
75710	NaN	Completed	6666.666667	Not displayed	NaN	36	NaN	NaN	C	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.09451	NaN	0.10000	NaN	NaN	NaN	4000
78414	NaN	Completed	8333.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01289	NaN	0.13000	NaN	NaN	NaN	2000
80369	NaN	Completed	4166.666667	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.09802	NaN	0.06500	NaN	NaN	NaN	2689
81848	NaN	Completed	1083.333333	Not displayed	NaN	36	NaN	NaN	D	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.38380	NaN	0.13000	NaN	NaN	NaN	4000
90598	NaN	Completed	16666.666667	Not displayed	NaN	36	NaN	NaN	B	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01051	NaN	0.12000	NaN	NaN	NaN	1000
92516	NaN	Completed	12500.000000	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.04569	NaN	0.07000	NaN	NaN	NaN	3500
103509	NaN	Completed	12500.000000	Not displayed	NaN	36	NaN	NaN	A	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.07015	NaN	0.09450	NaN	NaN	NaN	8998
105925	NaN	Completed	6666.666667	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.02743	NaN	0.08500	NaN	NaN	NaN	5000
106465	NaN	Completed	4166.666667	Not displayed	NaN	36	NaN	NaN	NC	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.03826	NaN	0.09000	NaN	NaN	NaN	4800
106735	NaN	Completed	14583.333333	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01747	NaN	0.05950	NaN	NaN	NaN	1500
109027	NaN	Completed	25000.000000	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.02217	NaN	0.06000	NaN	NaN	NaN	3000
111607	NaN	Completed	16666.666667	Not displayed	NaN	36	NaN	NaN	B	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.01404	NaN	0.06500	NaN	NaN	NaN	3000
113921	NaN	Completed	12500.000000	Not displayed	NaN	36	NaN	NaN	AA	NaN	NaN	False	NaN	NaN	NaN	NaN	NaN	0.23284	NaN	0.04000	NaN	NaN	NaN	1000

	EstimatedReturn	LoanStatus	StatedMonthlyIncome	IncomeRange	DelinquenciesLast7Years	Term	AmountDelinquent	ProsperScore	CreditGrade	EmploymentStatus	EmploymentStatusDuration	IsBorrowerHomeowner	CreditScoreRangeLower	CreditScoreRangeUpper	CurrentCreditLines	OpenCreditLines	RevolvingCreditBalance	DebtToIncomeRatio	BorrowerAPR	BorrowerRate	AvailableBankcardCredit	ProsperRating (Alpha)	ProsperRating (numeric)	LoanOriginalAmount
0	NaN	Completed	3083.333333	$25,000-49,999	4.0	36	472.0	NaN	C	Self-employed	2.0	True	640.0	659.0	5.0	4.0	0.0	0.17	0.16516	0.1580	1500.0	NaN	NaN	9425
1	0.05470	Current	6125.000000	$50,000-74,999	0.0	36	0.0	7.0	NaN	Employed	44.0	False	680.0	699.0	14.0	14.0	3989.0	0.18	0.12016	0.0920	10266.0	A	6.0	10000
2	NaN	Completed	2083.333333	Not displayed	0.0	36	NaN	NaN	HR	Not available	NaN	False	480.0	499.0	NaN	NaN	NaN	0.06	0.28269	0.2750	NaN	NaN	NaN	3001
3	0.06000	Current	2875.000000	$25,000-49,999	14.0	36	10056.0	9.0	NaN	Employed	113.0	True	800.0	819.0	5.0	5.0	1444.0	0.15	0.12528	0.0974	30754.0	A	6.0	10000
4	0.09066	Current	9583.333333	$100,000+	0.0	36	0.0	4.0	NaN	Employed	44.0	True	680.0	699.0	19.0	19.0	6193.0	0.26	0.24614	0.2085	695.0	D	3.0	15000

	EstimatedReturn	StatedMonthlyIncome	DelinquenciesLast7Years	Term	AmountDelinquent	ProsperScore	EmploymentStatusDuration	CreditScoreRangeLower	CreditScoreRangeUpper	CurrentCreditLines	OpenCreditLines	RevolvingCreditBalance	DebtToIncomeRatio	BorrowerAPR	BorrowerRate	AvailableBankcardCredit	ProsperRating (numeric)	LoanOriginalAmount
count	84853.000000	1.139120e+05	112947.000000	113912.000000	106315.000000	84853.000000	106312.000000	113346.000000	113346.000000	106333.000000	106333.000000	1.063330e+05	105358.000000	113912.000000	113912.000000	106393.000000	84853.000000	113912.000000
mean	0.096068	5.606973e+03	4.154984	40.831308	984.507059	5.950067	96.071582	685.567731	704.567731	10.317192	9.260164	1.759871e+04	0.275993	0.218828	0.192786	11210.225447	4.072243	8338.015661
std	0.030403	7.478338e+03	10.160216	10.437112	7158.270157	2.376501	94.480605	66.458275	66.458275	5.457866	5.022644	3.293640e+04	0.551814	0.080364	0.074809	19818.361309	1.673227	6245.940592
min	-0.182700	0.000000e+00	0.000000	12.000000	0.000000	1.000000	0.000000	0.000000	19.000000	0.000000	0.000000	0.000000e+00	0.000000	0.006530	0.000000	0.000000	1.000000	1000.000000
25%	0.074080	3.200000e+03	0.000000	36.000000	0.000000	4.000000	26.000000	660.000000	679.000000	7.000000	6.000000	3.121000e+03	0.140000	0.156290	0.134000	880.000000	3.000000	4000.000000
50%	0.091700	4.666667e+03	0.000000	36.000000	0.000000	6.000000	67.000000	680.000000	699.000000	10.000000	9.000000	8.549000e+03	0.220000	0.209760	0.184000	4100.000000	4.000000	6500.000000
75%	0.116600	6.817083e+03	3.000000	36.000000	0.000000	8.000000	137.000000	720.000000	739.000000	13.000000	12.000000	1.952100e+04	0.320000	0.283810	0.250000	13180.000000	5.000000	12000.000000
max	0.283700	1.750003e+06	99.000000	60.000000	463881.000000	11.000000	755.000000	880.000000	899.000000	59.000000	54.000000	1.435667e+06	10.010000	0.512290	0.497500	646285.000000	7.000000	35000.000000

	EstimatedReturn	LoanStatus	StatedMonthlyIncome	IncomeRange	DelinquenciesLast7Years	Term	AmountDelinquent	ProsperScore	CreditGrade	EmploymentStatus	EmploymentStatusDuration	IsBorrowerHomeowner	CreditScoreRangeLower	CreditScoreRangeUpper	CurrentCreditLines	OpenCreditLines	RevolvingCreditBalance	DebtToIncomeRatio	BorrowerAPR	BorrowerRate	AvailableBankcardCredit	ProsperRating (Alpha)	ProsperRating (numeric)	LoanOriginalAmount	creditscore
9	0.04231	Current	3333.333333	$25,000-49,999	0.0	36	0.0	11.0	NaN	Employed	269.0	True	820.0	839.0	17.0	16.0	9906.0	0.25	0.07620	0.0629	77696.0	AA	7.0	10000	829.5
69	0.06499	Current	2700.000000	$25,000-49,999	0.0	60	0.0	11.0	NaN	Self-employed	12.0	True	700.0	719.0	5.0	5.0	19961.0	NaN	0.13636	0.1139	5039.0	A	6.0	9000	709.5
158	0.04929	Current	6666.666667	$75,000-99,999	5.0	36	15599.0	11.0	NaN	Employed	22.0	False	700.0	719.0	9.0	8.0	2564.0	0.05	0.09469	0.0809	14737.0	AA	7.0	5500	709.5
224	0.06388	Current	33333.333333	$100,000+	0.0	36	0.0	11.0	NaN	Employed	114.0	True	720.0	739.0	16.0	16.0	55769.0	0.11	0.13799	0.1099	103931.0	A	6.0	30000	729.5
236	0.04261	Current	4083.333333	$25,000-49,999	0.0	36	0.0	11.0	NaN	Employed	105.0	True	820.0	839.0	11.0	11.0	4242.0	0.14	0.06726	0.0605	62608.0	AA	7.0	9000	829.5
277	0.07192	Current	6833.333333	$75,000-99,999	0.0	60	0.0	11.0	NaN	Full-time	154.0	False	680.0	699.0	10.0	8.0	23082.0	0.19	0.15868	0.1355	29368.0	B	5.0	20000	689.5
476	0.06491	Current	13083.333333	$100,000+	0.0	60	0.0	11.0	NaN	Employed	27.0	False	720.0	739.0	25.0	24.0	33126.0	0.29	0.14528	0.1224	4353.0	B	5.0	15000	729.5
491	0.07463	Current	8166.666667	$75,000-99,999	0.0	60	0.0	11.0	NaN	Employed	117.0	True	680.0	699.0	8.0	6.0	2748.0	0.18	0.17327	0.1500	4328.0	B	5.0	25000	689.5
532	0.06388	Current	10833.333333	$100,000+	0.0	36	0.0	11.0	NaN	Other	0.0	True	680.0	699.0	17.0	15.0	37603.0	0.15	0.13799	0.1099	136872.0	A	6.0	10000	689.5
554	0.04929	Current	15000.000000	$100,000+	0.0	60	0.0	11.0	NaN	Employed	80.0	True	820.0	839.0	10.0	10.0	689.0	0.04	0.09367	0.0809	59911.0	AA	7.0	20000	829.5
633	0.05879	Current	15000.000000	$100,000+	0.0	36	0.0	11.0	NaN	Employed	21.0	True	740.0	759.0	20.0	20.0	46429.0	0.22	0.12691	0.0990	86307.0	A	6.0	30000	749.5
690	0.06663	Current	4500.000000	$50,000-74,999	0.0	60	0.0	11.0	NaN	Employed	133.0	True	720.0	739.0	19.0	16.0	14575.0	0.25	0.13227	0.1099	11800.0	A	6.0	15000	729.5
765	0.07077	Current	8458.250000	$100,000+	0.0	60	0.0	11.0	NaN	Employed	210.0	True	740.0	759.0	18.0	18.0	32325.0	0.41	0.15425	0.1314	80375.0	B	5.0	15000	749.5
771	0.05516	Current	9333.333333	$100,000+	0.0	36	0.0	11.0	NaN	Employed	166.0	True	700.0	719.0	13.0	13.0	50301.0	0.21	0.10038	0.0869	60723.0	AA	7.0	19000	709.5
854	0.06910	Current	5416.666667	$50,000-74,999	0.0	60	0.0	11.0	NaN	Employed	20.0	False	780.0	799.0	11.0	11.0	5222.0	0.48	0.14658	0.1239	32378.0	A	6.0	15000	789.5
890	0.07077	Current	14333.333333	$100,000+	0.0	60	0.0	11.0	NaN	Employed	96.0	True	700.0	719.0	12.0	11.0	113816.0	0.12	0.15425	0.1314	23727.0	B	5.0	25000	709.5
901	0.06499	Current	16666.666667	$100,000+	0.0	60	0.0	11.0	NaN	Employed	91.0	True	740.0	759.0	16.0	16.0	7302.0	0.16	0.13636	0.1139	45898.0	A	6.0	23695	749.5
1017	0.04261	Current	4666.666667	$50,000-74,999	0.0	36	0.0	11.0	NaN	Other	0.0	True	720.0	739.0	15.0	15.0	15954.0	0.25	0.07957	0.0659	29682.0	AA	7.0	15000	729.5
1085	0.04929	Current	2641.666667	$25,000-49,999	0.0	36	0.0	11.0	NaN	Employed	42.0	True	740.0	759.0	13.0	12.0	4841.0	0.39	0.09434	0.0809	10894.0	AA	7.0	8500	749.5
1153	0.04806	Current	6250.000000	$75,000-99,999	0.0	36	0.0	11.0	NaN	Employed	75.0	True	700.0	719.0	19.0	19.0	3893.0	0.18	0.09030	0.0769	11470.0	AA	7.0	8000	709.5
1460	0.06663	Current	5009.750000	$50,000-74,999	0.0	36	0.0	11.0	NaN	Employed	131.0	False	680.0	699.0	10.0	9.0	31072.0	0.24	0.13799	0.1099	5121.0	A	6.0	8000	689.5
1842	0.04260	Current	8608.250000	$100,000+	0.0	36	0.0	11.0	NaN	Employed	45.0	True	780.0	799.0	20.0	20.0	14531.0	0.26	0.06726	0.0605	112969.0	AA	7.0	10000	789.5
1892	0.06081	Current	7500.000000	$75,000-99,999	0.0	36	0.0	11.0	NaN	Employed	100.0	True	680.0	699.0	11.0	11.0	22174.0	0.21	0.13189	0.1039	14199.0	A	6.0	20000	689.5
1962	0.06663	Current	4000.000000	$25,000-49,999	0.0	60	0.0	11.0	NaN	Employed	120.0	True	720.0	739.0	9.0	7.0	9421.0	0.28	0.13227	0.1099	22010.0	A	6.0	14326	729.5
1972	0.07689	Current	2500.000000	$25,000-49,999	0.0	36	0.0	11.0	NaN	Self-employed	173.0	True	660.0	679.0	11.0	11.0	7841.0	NaN	0.17090	0.1349	21163.0	B	5.0	4000	669.5
2048	0.04554	Current	10416.666667	$100,000+	0.0	36	0.0	11.0	NaN	Employed	140.0	True	740.0	759.0	11.0	11.0	42965.0	0.16	0.08496	0.0716	42611.0	AA	7.0	13000	749.5
2097	0.06706	Current	16750.000000	$100,000+	0.0	60	0.0	11.0	NaN	Employed	53.0	True	700.0	719.0	9.0	8.0	60618.0	0.15	0.14147	0.1189	5568.0	A	6.0	25000	709.5
2181	0.08223	Current	8750.000000	$100,000+	0.0	60	0.0	11.0	NaN	Employed	39.0	True	680.0	699.0	19.0	17.0	73564.0	0.37	0.21166	0.1875	33116.0	C	4.0	4500	689.5
2288	0.05879	Current	11250.000000	$100,000+	0.0	36	0.0	11.0	NaN	Employed	23.0	True	720.0	739.0	19.0	18.0	61476.0	0.25	0.12727	0.0990	74681.0	A	6.0	35000	729.5
2487	0.04260	Current	16666.666667	$100,000+	0.0	36	0.0	11.0	NaN	Self-employed	234.0	True	760.0	779.0	19.0	17.0	23274.0	NaN	0.06726	0.0605	65726.0	AA	7.0	15000	769.5
2548	0.04260	Current	8916.666667	$100,000+	0.0	36	0.0	11.0	NaN	Employed	101.0	True	800.0	819.0	10.0	8.0	5627.0	0.11	0.06726	0.0605	21415.0	AA	7.0	5000	809.5
2550	0.04529	Current	9583.333333	$100,000+	0.0	36	0.0	11.0	NaN	Employed	49.0	True	780.0	799.0	8.0	6.0	5898.0	0.11	0.07922	0.0659	8203.0	AA	7.0	12000	789.5
2644	0.06499	Current	5833.333333	$50,000-74,999	0.0	60	0.0	11.0	NaN	Employed	12.0	False	700.0	719.0	10.0	10.0	23490.0	0.27	0.13636	0.1139	24097.0	A	6.0	20000	709.5
2913	0.07077	Current	6833.333333	$75,000-99,999	0.0	60	0.0	11.0	NaN	Employed	13.0	False	680.0	699.0	7.0	7.0	5076.0	0.08	0.15425	0.1314	40224.0	B	5.0	5000	689.5
3006	0.06663	Current	6916.666667	$75,000-99,999	12.0	36	0.0	11.0	NaN	Employed	421.0	False	680.0	699.0	5.0	3.0	726.0	0.11	0.13799	0.1099	1274.0	A	6.0	5000	689.5
3067	0.04554	Current	9583.333333	$100,000+	0.0	36	0.0	11.0	NaN	Employed	243.0	True	740.0	759.0	11.0	11.0	69386.0	0.15	0.08496	0.0716	28768.0	AA	7.0	15000	749.5
3091	0.04261	Current	6250.000000	$75,000-99,999	0.0	36	0.0	11.0	NaN	Employed	14.0	False	780.0	799.0	11.0	11.0	10889.0	0.30	0.06726	0.0605	16111.0	AA	7.0	12000	789.5
3136	0.07824	Current	2114.916667	$25,000-49,999	0.0	36	0.0	11.0	NaN	Employed	49.0	False	660.0	679.0	11.0	9.0	4307.0	0.48	0.20524	0.1685	8793.0	C	4.0	4000	669.5
3156	0.04929	Current	5333.333333	$50,000-74,999	0.0	36	577.0	11.0	NaN	Employed	173.0	False	700.0	719.0	11.0	11.0	23777.0	0.25	0.09434	0.0809	64165.0	AA	7.0	15000	709.5
3189	0.07078	Current	11666.666667	$100,000+	0.0	36	0.0	11.0	NaN	Employed	287.0	True	720.0	739.0	10.0	10.0	49829.0	0.23	0.14816	0.1199	33971.0	A	6.0	35000	729.5

Part II - (Explanatory analysis of Loan Data)¶

by (Williams Miebi Gbeneowei)¶

Investigation Overview:¶

Dataset Overview¶

DATA SET:¶

As seen above from the first assessment, there are a whooping 81 columns and over 110,000 rows of data, We will not be needing all those columns, we will keep only columns relevant to the insights to be gotten from the data and possibly delete some rows of data as well if neccessary.¶

Univariate Exploration¶

Univariate plots¶

Borrower APR and Borrower Rate.¶

Observation:¶

Income Range¶

Original Loan Amount¶

Distribution of credit score¶

OBSERVATION¶

Stated Monthly Income¶

OBSERVATION¶

Loan Term¶

Employment Status,Loanterm and ProsperRating¶

Observation:¶

Employment Status column:¶

Prosper rating:¶

Term:¶

Prosper Rating¶

OBSERVATION¶

Delinquencies and amount deliquent¶

Observation:¶

DelinquenciesLast7Years¶

OBSERVATION¶

current credit lines¶

Observation:¶

Distribution of open credit line¶

Observation:¶

Revolvingcredit balance:¶

Observation:¶

Available bank credit¶

Observation:¶

INSIGHTS¶

1.What are the factors that affect a loans outcome status?¶

2.What factors affects the borrower APR?¶

3.Does the term of the loan affect the annual percentage rate(Borrower's APR) of the borrower?¶

Insight1.¶

What Factors affects a loan's outcome status?:¶

BIVARIATE EXPLORATION¶

General overview of correlation between variables¶

Creditscore and prosper score¶

Observation:¶

Is BorrowerHome owner or not¶

OBSERVATION:¶

Loan Original Amount and Prosper score¶

Observation:¶

How employment Status Affects Prosper Rating¶

Observation:¶

How does the debt to income ratio affect the client's prosper score?¶

Observation:¶

How Revolving Credit balance affects prosper score¶

Observation:¶

Stated Monthly Income and Prosper score¶

Observation:¶

Stated Monthly Income and Prosper score. and terms¶

Term and Prosper Score¶

Observation:¶

INSIGHT 1 SUMMARY FOR BIVARIATE ANALYSIS:¶

Insight 2¶

What Affects the borrowers APR or interest rates¶

Interaction of of numeric and categorical features.¶

Borrower APR and Prosper score¶

Observation:¶

Borrower APR and prosper rating¶

Observation:¶

Borrower APR and DebtTo income ratio¶

Observation:¶

Borrower APR and Creditscore¶

How does the creditscore affect the borrower APR?¶

Observation:¶

BorrowerAPR and DelinquenciesLast7Years¶

Observation:¶

Observation:¶

Does Employment Status affect the borrower APR?¶

Observation:¶

INSIGHT 2 SUMMARY FOR BIVARIATE ANALYSIS:¶